Prof. Dr.

Schmitt, Robert

Filters

Reset filters

Settings
Now showing 1 - 10 of 678
  • Publication
    Ready for Take-off - Artificial Intelligence in Space Production
    ( 2024-07-09)
    Schuh, Günther
    ;
    Schmitt, Robert H.
    ;
    Cassel, Leonard
    ;
    Schenk, Leonard
    ;
    Motz, Maximilian
    This whitepaper explores the potential and challenges of applying Artificial Intelligence (AI) in the production of aerospace components. Through various research activities at Fraunhofer IPT, six promising application fields for AI use have been identified: predictive quality in the manufacturing of complex parts, predictive maintenance for critical machines, automated evaluation of test processes, support for documentation tasks through generative language models, creation of digital twins, and adaptive process monitoring for specialized manufacturing procedures. The implementation of AI in aerospace production is hindered by limited data availability and complex qualification processes. The whitepaper presents a systematic approach that includes the identification, evaluation, prioritization, and piloting of use cases. The goal is to develop the necessary capabilities within the company to independently carry out future AI projects and maximize their benefits. The findings emphasize the need for a strategic and methodical approach to integrating AI into aerospace production to achieve efficiency gains and increase competitiveness.
  • Publication
    Ready for Take-off - Künstliche Intelligenz in der Raumfahrtproduktion
    ( 2024-07-09)
    Schuh, Günther
    ;
    Schmitt, Robert H.
    ;
    Cassel, Leonard
    ;
    Schenk, Leonard
    ;
    Motz, Maximilian
    Dieses Whitepaper untersucht das Potenzial und die Herausforderungen der Anwendung von Künstlicher Intelligenz (KI) in der Produktion von Raumfahrtkomponenten. Durch Forschungsaktivitäten des Fraunhofer IPT wurden sechs vielversprechende Anwendungsfelder für den Einsatz von KI identifiziert: Predictive-Quality in der Fertigung komplexer Bauteile, Predictive-Maintenance für kritische Maschinen, automatisierte Auswertung von Testprozessen, Unterstützung bei Dokumentationstätigkeiten durch generative Sprachmodelle, Erstellung digitaler Zwillinge und adaptive Prozessüberwachung für spezialisierte Fertigungsverfahren. Die Implementierung von KI in der Raumfahrtproduktion wird durch geringe Datenverfügbarkeit und aufwändige Qualifizierungsprozesse erschwert. Das Whitepaper stellt einen systematischen Ansatz vor, der die Identifizierung, Bewertung, Priorisierung und Pilotierung von Use Cases umfasst. Ziel ist es, langfristig die notwendigen Fähigkeiten im Unternehmen aufzubauen, um zukünftige KI-Projekte eigenständig durchzuführen und deren Nutzen zu maximieren. Die Ergebnisse betonen die Notwendigkeit eines strategischen und methodischen Vorgehens bei der Integration von KI in die Raumfahrtproduktion, um Effizienzsteigerungen zu realisieren und die Wettbewerbsfähigkeit der Raumfahrtstandorts Deutschland zu erhöhen.
  • Publication
    A concept for a large-scale non-contact strain measurement system using nanostructures
    ( 2024-06-24)
    Ulm, Andreas
    ;
    König, Niels orcid-logo
    ;
    Schmitt, Robert
    The monitoring of mechanical strain is essential in developing new materials, designing mechanical components and structural health monitoring. In applications where contactless measurement is required, a novel method is needed to allow for absolute and long-term measurements. We discuss a measuring principle based on diffractive nanostructures featuring these advantages. For the measurement, periodic nanostructures are applied to a component, illuminated with a defined light source and the resulting color impression is monitored. The relationship between the stretched geometry of the nanostructure and diffraction spectra allows to quantify the component’s strain. We present a guide-line for the design of industrial applicable and sensitivity-optimized nanostructures and discuss the advantages in different application scenarios.
  • Publication
    Diffractive nanostructures for angle calibration of optical metrology systems
    ( 2024-05-13)
    Schmitt, Robert
    ;
    Ulm, Andreas
    Mobile optical metrology techniques face the problem of difficult alignment, e.g., in strain metrology of moving parts or for regular inspections. This time-consuming and costly step might become faster by an active angle calibration with diffractive nanostructures.We propose a design for diffractive nanostructures which allow for an active angle calibration.
  • Publication
    Holistic Approach for Digitalized Quality Assurance in Battery Cell Production
    ( 2024-01-12)
    Kies, Alexander
    ;
    Abramowski, Johann-Philip
    ;
    Ackermann, Thomas orcid-logo
    ;
    Kux, Fabian Austen
    ;
    Kreppein, Alexander
    ;
    Grunert, Dennis
    ;
    Schmitt, Robert H.
    In this paper, we introduce a holistic approach to consider quality assurance (QA) for battery cell production (BCP). The framework, the explanation of the individual components as well as their interfaces and dependencies, and a detailed description are presented. Firstly, the level of necessary data (e. g. provided by online and out-of-line measurement systems) for the inspection of quality is presented. The aggregation of the recorded data as well as their tracing are ensured by the realization of a traceability system. Subsequently, by defining a suitable intelligent quality gate system, QA mechanisms are implemented and an active influence on production - e. g. by adaptive process control or identifying and reducing negative influence of cause-effect relationships - is aimed at. Finally, optimization of BCP in terms of product quality and its sustainability will be enabled. The evaluation of the demonstrated approach in practice is outlined based on an exemplary process of BCP.
  • Publication
    Wie Machine Learning auf dem Shopfloor die Produktionsqualität steigert. Intelligente Qualitätsplattform
    ( 2024-01-04)
    Frye, Maik
    ;
    Hellmich, Jan Hendrik orcid-logo
    ;
    Leyendecker, Lars orcid-logo
    ;
    Motz, Maximilian
    ;
    Gabriel, Alexander
    ;
    Heymann, Henrik orcid-logo
    ;
    Grunert, Dennis
    ;
    Schmitt, Robert
    Mit der intelligenten Qualitätsplattform (IQP) wurde am Fraunhofer-Institut für Produktionstechnologie IPT eine Management-Plattform zur Nutzung, Überwachung und fortlaufenden Optimierung verschiedener ML-Anwendungen entwickelt. Dazu zählen prädiktive Wartung von Maschinen, Vorhersage der Produktqualität oder das Erkennen von Maschinenauffälligkeiten. Die IQP dient dazu, verschiedene ML-Anwendungen aus unterschiedlichen Produktionsbereichen standardisiert zu integrieren und parallel zu betreiben.
  • Publication
    Machine learning pipeline for application in manufacturing
    ( 2024)
    Fitzner, Antje orcid-logo
    ;
    Hülsmann, Tom orcid-logo
    ;
    Ackermann, Thomas orcid-logo
    ;
    Pouls, Kevin Bernard
    ;
    Krauß, Jonathan orcid-logo
    ;
    Mende, Hendrik
    ;
    Leyendecker, Lars orcid-logo
    ;
    Schmitt, Robert
    The integration of machine learning (ML) into manufacturing processes is crucial for optimizing efficiency, reducing costs, and enhancing overall productivity. This paper proposes a comprehensive ML pipeline tailored for manufacturing applications, leveraging the widely recognized Cross-Industry Standard Process for Data Mining (CRISP-DM) as its foundational framework. The proposed pipeline consists of key phases, namely business understanding, use case selection and specification, data integration, data preparation, modelling, deployment, and certification. These are designed to meet the unique requirements and challenges associated with ML implementation in manufacturing settings. Within each phase, sub-topics are defined to provide a granular understanding of the workflow. Responsibilities are clearly outlined to ensure a structured and efficient execution, promoting collaboration among stakeholders. Further, the input and output of each phase are defined. The methodology outlined in this research not only enhances the applicability of CRISP-DM in the manufacturing domain but also serves as a guide for practitioners seeking to implement ML solutions in a systematic and well-defined manner. The proposed pipeline aims to streamline the integration of ML technologies into manufacturing processes, facilitating informed decision-making and fostering the development of intelligent and adaptive manufacturing systems.
  • Publication
    The Digital Twin Demonstrator
    ( 2023-11-27)
    Bäckel, Niklas
    ;
    Gilerson, Andre
    ;
    Kreppein, Alexander
    ;
    Schmitt, Robert H.